← Every GPUNVIDIA · 40 or 80 GB VRAM · 1555 GB/s

What can the A100 run?

With 40 GB, 8 of 12 popular open models fit. The best pick is Qwen3 32B at about 43 tok/s, faster than you can read.

ollama run qwen3:32b

First time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.

40 GB VRAM

Every model the A100 40 GB can run

8 of 12 fit. Best pick: Qwen3 32B.

  • Qwen3 4BQuick everyday chat and summaries
    ~340 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~160 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~110 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~92 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~270 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~50 tok/s
    Runs greatgemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~270 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~43 tok/s
    Runs greatqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    needs 45 GB
    Too bigllama3.3:70b
  • gpt-oss 120BOpenAI's largest open model
    needs 67 GB
    Too biggpt-oss:120b
  • Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigs
    needs 144 GB
    Too bigqwen3:235b
  • DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigs
    needs 406 GB
    Too bigdeepseek-r1:671b
80 GB VRAM

Every model the A100 80 GB can run

10 of 12 fit. Best pick: gpt-oss 120B.

  • Qwen3 4BQuick everyday chat and summaries
    ~340 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~160 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~110 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~92 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~270 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~50 tok/s
    Runs greatgemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~270 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~43 tok/s
    Runs greatqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~20 tok/s
    Usablellama3.3:70b
  • gpt-oss 120BOpenAI's largest open model
    ~190 tok/s
    Runs greatgpt-oss:120b
  • Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigs
    needs 144 GB
    Too bigqwen3:235b
  • DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigs
    needs 406 GB
    Too bigdeepseek-r1:671b
Common questions

Can the A100 run it?

Can the A100 run Llama 3.3 70B?

Yes, with 80 GB or more. Llama 3.3 70B needs about 45 GB and the A100 has 80 GB of VRAM. Expect about 20 tok/s, about reading speed. The 40 GB version doesn't have room.

Can the A100 run gpt-oss 120B?

Yes, with 80 GB or more. gpt-oss 120B needs about 67 GB and the A100 has 80 GB of VRAM. Expect about 190 tok/s, faster than you can read. The 40 GB version doesn't have room.

Can the A100 run Qwen3 235B-A22B?

No. Qwen3 235B-A22B needs about 144 GB and the A100 has at most 80 GB of VRAM. Ollama can still start it by putting part of the model in system RAM, but it runs several times slower. The most capable model it runs well is gpt-oss 120B, at about 190 tok/s.

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (1555 GB/s) divided by the active weight size, with efficiency calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured one yourself? Send us the number.

Want something bigger?

The Ryzen AI Max+ 395 mini PC, 128 GB runs gpt-oss 120B at about 31 tok/s, from $3,400 used.

See the builds

Compare

Similar cards

Every GPU we track

Head to head

The A100 against its rivals

Every comparison